Pith Number

pith:TTNY2ODJ

pith:2022:TTNY2ODJEGWATHHS3VDQJ3QXF2

not attested not anchored not stored refs resolved

CoCa: Contrastive Captioners are Image-Text Foundation Models

Jiahui Yu, Legg Yeung, Mojtaba Seyedhosseini, Vijay Vasudevan, Yonghui Wu, Zirui Wang

CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks.

arxiv:2205.01917 v2 · 2022-05-04 · cs.CV · cs.LG · cs.MM

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TTNY2ODJEGWATHHS3VDQJ3QXF2}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

CoCa obtains 86.3% zero-shot top-1 accuracy on ImageNet, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder, while also leading on Kinetics, MSCOCO, VQA, and other tasks.

C2weakest assumption

That omitting cross-attention in the first half of the decoder layers cleanly separates unimodal text representations from multimodal ones without harming overall capacity or optimization stability.

C3one line summary

CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.

References

80 extracted · 80 resolved · 15 Pith anchors

[1] On the Opportunities and Risks of Foundation Models 2021 · arXiv:2108.07258

[2] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2018 · arXiv:1810.04805

[3] Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer 1910 · arXiv:1910.10683

[4] Language models are few-shot learners 1901

[5] Thekkath, and Yonghui Wu 2022

Formal links

2 machine-checked theorem links

Cited by

41 papers in Pith

DAPL: Integration of Positive and Negative Descriptions in Text-Based Person Search

Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP

Character-Centered Dialogue Generation from Scene-Level Prompts

FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation

TextTeacher: What Can Language Teach About Images?

Receipt and verification

First computed	2026-05-17T23:38:52.732937Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562

Aliases

arxiv: 2205.01917 · arxiv_version: 2205.01917v2 · doi: 10.48550/arxiv.2205.01917 · pith_short_12: TTNY2ODJEGWA · pith_short_16: TTNY2ODJEGWATHHS · pith_short_8: TTNY2ODJ

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "33c64576bd99d3220fac09e2275b95093c5fe2928a27639a33ad2c3ad2b5f166",
    "cross_cats_sorted": [
      "cs.LG",
      "cs.MM"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2022-05-04T07:01:14Z",
    "title_canon_sha256": "979368834a9c1c63162fa1ef78acefae237399dabc836024cbfc08aa7f9b530b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2205.01917",
    "kind": "arxiv",
    "version": 2
  }
}